Multi-Modal Recurrent Fusion for Indoor Localization
This work addresses indoor localization for applications like navigation and tracking, but it is incremental as it builds on existing multi-modal and recurrent neural network approaches.
The paper tackles indoor localization by formulating it as a multi-modal sequence regression problem, using Wi-Fi, IMU, and UWB signals, and proposes a multi-stream recurrent fusion method that accounts for modality uncertainty; it achieves competitive results on the SPAWC2021 dataset compared to various baselines.
This paper considers indoor localization using multi-modal wireless signals including Wi-Fi, inertial measurement unit (IMU), and ultra-wideband (UWB). By formulating the localization as a multi-modal sequence regression problem, a multi-stream recurrent fusion method is proposed to combine the current hidden state of each modality in the context of recurrent neural networks while accounting for the modality uncertainty which is directly learned from its own immediate past states. The proposed method was evaluated on the large-scale SPAWC2021 multi-modal localization dataset and compared with a wide range of baseline methods including the trilateration method, traditional fingerprinting methods, and convolution network-based methods.